Skip to content

[HIGH PRIORITY] Fix indexing and update logging #102

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
shahmeer99 wants to merge 4 commits into
base: main
Choose a base branch
from
Open

[HIGH PRIORITY] Fix indexing and update logging #102

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
34c1f33
revert back to sequential encoding for index creation
Apr 8, 2026
8c0ff9a
update test cases to reflect changes in previous commit to variable n…
Apr 9, 2026
785cce7
add query contextualization to retriever when using qwen3 embedder. T…
Apr 9, 2026
50746e9
feat(api_server): add reranking, per-chunk retrieval diagnostics to l…
Apr 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions config/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,14 +1,15 @@
embed_model: "models/Qwen3-Embedding-4B-Q5_K_M.gguf"
embedding_model_context_window: 4096
Copy link
Copy Markdown
Contributor

@RajShah-1 RajShah-1 Apr 17, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Did we do a regression with new configs to ensure that we are improving/retaining performance?

top_k: 10
num_candidates: 50
ensemble_method: "rrf"
ranker_weights: {"faiss":1,"bm25":0,"index_keywords":0}
ranker_weights: {"faiss":0.75,"bm25":0.25,"index_keywords":0}
rrf_k: 60
max_gen_tokens: 400
chunk_mode : "recursive_sections"
chunk_mode: "recursive_sections"
gen_model: "models/qwen2.5-3b-instruct-q8_0.gguf"
chunk_size: 2000
chunk_overlap: 200
chunk_size_in_chars: 2000
chunk_overlap: 300
use_hyde: false
hyde_max_tokens: 300
use_indexed_chunks: false
Expand All @@ -17,4 +18,4 @@ rerank_top_k: 5
use_double_prompt: false
enable_history: true
max_history_turns: 3
enable_topic_extraction: true
enable_topic_extraction: false
Loading
Loading